Papers with Code 아카이브

Adversarial Defense

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

2

평가표

10

보존된 평가 기록

28

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/cychomatica/audiopure

공식 코드

Defending against Adversarial Audio via Diffusion Model

https://github.com/ddkang/advex-uar

공식 코드

Testing Robustness Against Unforeseen Adversaries

https://github.com/deep-kaixun/videopure

공식 코드

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

https://github.com/deepgenerativeclassifier/DeepBayes

공식 코드

Are Generative Classifiers More Robust to Adversarial Attacks?

https://github.com/distrinet/flowpure

공식 코드

FlowPure: Continuous Normalizing Flows for Adversarial Purification

https://github.com/dravyanshsharma/adversarial-contrastive

공식 코드

An Analysis of Robustness of Non-Lipschitz Networks

https://github.com/dvlab-research/LBGAT

공식 코드

Learnable Boundary Guided Adversarial Training

https://github.com/dwdavidxd/man

공식 코드

Modeling Adversarial Noise for Adversarial Training

https://github.com/dwdavidxd/miat

공식 코드

Improving Adversarial Robustness via Mutual Information Estimation

https://github.com/dydjw9/RAIN

공식 코드

RAIN: A Simple Approach for Robust and Accurate Image Classification Networks

https://github.com/edisonleeeee/guard

공식 코드

GUARD: Graph Universal Adversarial Defense

https://github.com/ellezwq/mmcoa

공식 코드

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

https://github.com/elliothe/CVPR_2019_PNI

공식 코드

Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack

https://github.com/emaballarin/CARSO

공식 코드

Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness

https://github.com/ericyu97/uad-rs

공식 코드

Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models

https://github.com/eth-sri/diffai

공식 코드

A Provable Defense for Deep Residual Networks

https://github.com/eth-sri/transformation-smoothing

공식 코드

Certified Defense to Image Transformations via Randomized Smoothing

https://github.com/ethanrath/game-theoretic-mixed-experts

공식 코드

Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning

https://github.com/evaluating-adversarial-robustness/adv-eval-paper

공식 코드

On Evaluating Adversarial Robustness

https://github.com/facebookresearch/ImageNet-Adversarial-Training

공식 코드

Feature Denoising for Improving Adversarial Robustness

https://github.com/facebookresearch/adversarial_image_defenses

공식 코드

Countering Adversarial Images using Input Transformations

https://github.com/finger-monkey/Data-Augmentation

공식 코드

Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method

https://github.com/finger-monkey/ReID_Adversarial_Defense

공식 코드

A Person Re-identification Data Augmentation Method with Adversarial Defense Effect

https://github.com/fiveai/parot

공식 코드

PaRoT: A Practical Framework for Robust Deep Neural Network Training

https://github.com/fra31/auto-attack

공식 코드

Learnable Boundary Guided Adversarial Training

https://github.com/glin2022/atop

공식 코드

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

https://github.com/gq-max/advdiffvlm

공식 코드

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models

https://github.com/guanjiyang/sac

공식 코드

Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks

https://github.com/guanjiyang/sac_jc

공식 코드

Sample Correlation for Fingerprinting Deep Face Recognition

https://github.com/h-chang/UniBERT

공식 코드

Unitary Multi-Margin BERT for Robust Natural Language Processing

https://github.com/haibinzheng/SFE

공식 코드

Salient Feature Extractor for Adversarial Defense on Deep Neural Networks

https://github.com/hala64/udp

공식 코드

Detection and Defense of Unlearnable Examples

https://github.com/harrywuhust2022/Adv-Crowd-analysis

공식 코드

Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting

https://github.com/hendrycks/robustness

공식 코드

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

https://github.com/hondamunigeprasannasilva/diffdefence

공식 코드

DiffDefense: Defending against Adversarial Attacks via Diffusion Models

https://github.com/huanranchen/AdversarialAttacks

공식 코드

Robust Classification via a Single Diffusion Model

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.